Imagen de Portada

Automating Agent Hijacking via Structural Template Injection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Deng, Xinhao, Wu, Jiaqing, Chen, Miao, Xiao, Yue, Xu, Ke, Li, Qi
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Robust and Reliable Early-Stage Website Fingerprinting Attacks via Spatial-Temporal Distribution Analysis
por: Deng, Xinhao, et al.
Publicado: (2024)

AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
por: Zhang, Yixiang, et al.
Publicado: (2026)

RF-Agent: Automated Reward Function Design via Language Agent Tree Search
por: Gao, Ning, et al.
Publicado: (2026)

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
por: Xu, Zhiyuan, et al.
Publicado: (2026)

Learning to Inject: Automated Prompt Injection via Reinforcement Learning
por: Chen, Xin, et al.
Publicado: (2026)

CleanAgent: Automating Data Standardization with LLM-based Agents
por: Qi, Danrui, et al.
Publicado: (2024)

$Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation
por: Wei, Yuan, et al.
Publicado: (2025)

ChemAmp: Amplified Chemistry Tools via Composable Agents
por: Li, Zhucong, et al.
Publicado: (2025)

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning
por: Jing, Zihao, et al.
Publicado: (2025)

CHAI: Command Hijacking against embodied AI
por: Burbano, Luis, et al.
Publicado: (2025)

Beyond a Single Perspective: Towards a Realistic Evaluation of Website Fingerprinting Attacks
por: Deng, Xinhao, et al.
Publicado: (2025)

On the Robustness of Transformers against Context Hijacking for Linear Classification
por: Li, Tianle, et al.
Publicado: (2025)

Efficient Graph Understanding with LLMs via Structured Context Injection
por: Waghmare, Govind, et al.
Publicado: (2025)

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
por: Zhang, Jiawei, et al.
Publicado: (2025)

Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation
por: Zhao, Ke, et al.
Publicado: (2024)

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
por: Feng, Xinshun, et al.
Publicado: (2026)

Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning
por: Wu, Lisheng, et al.
Publicado: (2024)

Hijack Vertical Federated Learning Models As One Party
por: Qiu, Pengyu, et al.
Publicado: (2022)

In-Context Representation Hijacking
por: Yona, Itay, et al.
Publicado: (2025)

Improving Value-based Process Verifier via Structural Prior Injection
por: Sun, Zetian, et al.
Publicado: (2025)

AgentKit: Structured LLM Reasoning with Dynamic Graphs
por: Wu, Yue, et al.
Publicado: (2024)

Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design
por: Huang, Zixiao, et al.
Publicado: (2025)

Could Chemical LLMs benefit from Message Passing
por: Xie, Jiaqing, et al.
Publicado: (2024)

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
por: Lu, Yao, et al.
Publicado: (2025)

Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer
por: Wang, Yongyi, et al.
Publicado: (2026)

FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models
por: Wang, Xiaochen, et al.
Publicado: (2024)

Automated Formalization via Conceptual Retrieval-Augmented LLMs
por: Lu, Wangyue, et al.
Publicado: (2025)

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
por: Chen, Hui, et al.
Publicado: (2025)

SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing
por: Ke, Junlong, et al.
Publicado: (2025)

Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection
por: Peng, Yihang, et al.
Publicado: (2026)

MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization
por: Fu, Tianfan, et al.
Publicado: (2020)

Adversarial Training for Robust Coverage Network under Worst-case Facility Losses
por: Miao, Changhao, et al.
Publicado: (2026)

Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts
por: Miao, Changhao, et al.
Publicado: (2026)

An End-to-End Learning Approach for Solving Capacitated Location-Routing Problems
por: Miao, Changhao, et al.
Publicado: (2025)

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
por: Wang, Hao, et al.
Publicado: (2026)

Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
por: Zhang, Wengyu, et al.
Publicado: (2026)

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
por: Hou, Hongru, et al.
Publicado: (2026)

Diversity Optimization for Travelling Salesman Problem via Deep Reinforcement Learning
por: Li, Qi, et al.
Publicado: (2025)

TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation
por: Cui, Tianyu, et al.
Publicado: (2025)

GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
por: Cao, Yuan, et al.
Publicado: (2026)